deepseek-v4.1-flash-1017-exl3-2.7bpw-vllm-2x-dgx-spark
deepseek-v4.1-flash-1017-exl3-2.7bpw-vllm-2x-dgx-spark is DeepSeek-V4.1-Flash-1017 (763B) on 2x DGX Spark: in-house mixed-K EXL3 2.7 bpw, vLLM TP=2, vision, 1M context. ./run.sh / ./stop.sh - sfxnz/DeepSeek-V4.1-Flash-1017-EXL3-2.7bpw-vLLM-2x-DGX-Spark. It is ranked #1716 on the Dev Radar, in AI dev tools, first seen 11 days ago and shared in 2 posts (5.7k views).
GitHub - sfxnz/DeepSeek-V4.1-Flash-1017-EXL3-2.7bpw-vLLM-2x-DGX-Spark: DeepSeek-V4.1-Flash-1017 (763B) on 2x DGX Spark: in-house mixed-K EXL3 2.7 bpw, vLLM TP=2, vision, 1M context. ./run.sh / ./stop.sh · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation DeepSeek-V4.1-Flash-1017-EXL3-2.7bpw-vLLM-2x-DGX-Spark…
What people said about deepseek-v4.1-flash-1017-exl3-2.7bpw-vllm-2x-dgx-spark on X
DeepSeek V4.1 Flash 1017 now handles requests like the official API. deepseek-recipe now fronts vLLM: • prompts token identical to the API • thinking, effort, JSON schema, tools fixed • Chat, Anthropic & Responses API's • no speed cost Local. Free…
— @sfxnz, 8 days ago · 70 likes · see the post
DeepSeek-V4.1-Flash-1017 on 2x DGX spark, quantised in-house to 2.7 bpw EXL3 🔥 - 40-50 tok/s decode - 1M context - Vision on vLLM - KL 0.025 vs the unquantised model This recipe will be significantly improved over time! ./run.sh and go https://github.com/sfxnz/DeepSeek-V4.1-Flash-1017-EXL3-2.7bpw-vLLM-2x-DGX-Spark
— @sfxnz, 11 days ago · 15 likes · see the post
Alternatives to deepseek-v4.1-flash-1017-exl3-2.7bpw-vllm-2x-dgx-spark
- goo.gle — Officially in beta, the AppFunctions API is opening up powerful new ways to integrate your functionality.
- Kimi AI with K3.1 Pro — Try Kimi K3.1 Pro to tackle complex coding projects, build 3D models, conduct financial research, and take on more…
- Agents in flight — Give it a try
- Baseten — This session is our most in-demand yet. See you there
- project-maya — Checkout Maya
- deepinfer — You gotta love Deepseek. This is awesome stuff!
deepseek-v4.1-flash-1017-exl3-2.7bpw-vllm-2x-dgx-spark in numbers
- Rank on the Dev Radar: #1716 of 8801
- Shared in 2 posts by 1 account: @sfxnz
- 5.7k views on those posts
- First seen 11 days ago, last shared 8 days ago
- Pricing seen by AGK Intelligence: free
- Market: AI dev tools
FAQ
What is deepseek-v4.1-flash-1017-exl3-2.7bpw-vllm-2x-dgx-spark?
DeepSeek-V4.1-Flash-1017 (763B) on 2x DGX Spark: in-house mixed-K EXL3 2.7 bpw, vLLM TP=2, vision, 1M context. ./run.sh / ./stop.sh - sfxnz/DeepSeek-V4.1-Flash-1017-EXL3-2.7bpw-vLLM-2x-DGX-Spark It was first shared on X 11 days ago and is ranked #1716 on the Dev Radar.
Is deepseek-v4.1-flash-1017-exl3-2.7bpw-vllm-2x-dgx-spark free?
Yes, it is free to use.
Who shared deepseek-v4.1-flash-1017-exl3-2.7bpw-vllm-2x-dgx-spark?
1 account on X, including @sfxnz, in 2 posts totalling 5.7k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 21:12 UTC. Full method.